作者位次 #3/4ACL 2026Findings· Findings of ACL
XGUARD : A Graded Benchmark for Evaluating Safety Failures of Large Language Models on Extremist Content
Vadivel Abishethvarman · Bhavik Chandna · Pratik Jalan · Usman Naseem
摘要
Large Language Models (LLMs) can generate content spanning ideological rhetoric to explicit instructions for violence. However, existing safety evaluations often rely on simplistic binary labels (safe/unsafe), overlooking the nuanced spectrum of risk these outputs pose. To address this, we presen...